Lightnews — Scholar-powered news

Bo Wang @bowang87.bsky.social · Mar 17

This pivotal work is the result of a collaborative effort led by Micaela E. Consens, with contributions from Cameron Dufault, Michael Wainberg, Duncan Forster, Mehran Karimzadeh, Hani Goodarzi, Fabian J. Theis, Alan Moses.

@uhnresearch.bsky.social
@vectorinstitute.ai
@uoft.bsky.social

1 1

Bo Wang @bowang87.bsky.social · Mar 17

⚡ Strengths, Limitations, & Future Directions: Gain insights into the current capabilities of genomic AI, its limitations, and the promising avenues for future research and application.

1

Bo Wang @bowang87.bsky.social · Mar 17

📊 Comparative Analysis of Models: We delve into the evolution from sequence-to-function models like DeepSEA and Enformer to sequence-to-sequence models such as DNABERT and Evo, highlighting their respective strengths and applications.

1

Bo Wang @bowang87.bsky.social · Mar 17

🚀 Beyond Transformers—Introducing HyenaDNA: Explore innovative architectures like HyenaDNA, which offer efficient long-range genomic sequence modeling at single nucleotide resolution, pushing the boundaries of genomic research.

1

Bo Wang @bowang87.bsky.social · Mar 17

🧠 Transformers in Genomics: Discover how transformer architectures, renowned for their success in natural language processing, are adept at capturing long-range dependencies in genomic data, leading to more accurate models.

1 1

Bo Wang @bowang87.bsky.social · Mar 17

Key Highlights:

🔬 The Challenges Addressed by gLMs: gLMs tackle the intricate task of interpreting vast genomic sequences, enabling predictions about gene regulation, variant effects, and more.

1

Bo Wang @bowang87.bsky.social · Mar 17

🔥 Unveiling the Future of Genomics with Genome Language Models (gLMs)! 🔥

Our comprehensive review, "Transformers and genome language models," is finally published in Nature Machine Intelligence!

Link: nature.com/articles/s42...

Transformers and genome language models - Nature Machine Intelligence

Micaela Consens et al. discuss and review the recent rise of transformer-based and large language models in genomics. They also highlight promising directions for genome language models beyond the tra...

nature.com

1 5 24

Bo Wang @bowang87.bsky.social · Feb 18

🙏 A huge team effort behind this work, with special appreciation to BowenLi Lab
for driving the project. Kudos to Haotian Cui, Yue Xu, Kuan Pang, Gen Li and Fanglin Gong!

Bo Wang @bowang87.bsky.social · Feb 18

🌐 Beyond mRNA drugs, LUMI-lab exemplifies a scalable framework for AI-driven molecular discovery, pushing boundaries in material science & drug delivery.
📜 Read the preprint: 🔗 biorxiv.org/content/10.1...
💻 Code available on GitHub: 🔗 github.com/bowenli-lab/...

LUMI-lab: a Foundation Model-Driven Autonomous Platform Enabling Discovery of New Ionizable Lipid Designs for mRNA Delivery

The complexity of molecular discovery requires autonomous systems that efficiently explore vast and uncharted chemical spaces. While integrating artificial intelligence (AI) with robotic automation ha...

biorxiv.org

1

Bo Wang @bowang87.bsky.social · Feb 18

🚀 Why it matters?
LNPs are the backbone of mRNA therapeutics, yet discovery has been slow due to data scarcity. LUMI-lab shows that AI-powered autonomous labs can accelerate mRNA delivery innovation🚀💡

1

Bo Wang @bowang87.bsky.social · Feb 18

- 1,700+ new LNPs synthesized & tested across 10 iterative cycles
- Brominated lipids autonomously identified as a novel structural feature that enhances mRNA transfection—an insight previously unrecognized in LNP design
- 20.3% in vivo CRISPR gene editing efficiency in lung epithelial cells

1

Bo Wang @bowang87.bsky.social · Feb 18

🔥 Key Highlights:
- Foundation model trained on 28M molecules using a three-step strategy:
- Unsupervised pretraining to capture broad molecular knowledge
- Continual pretraining to specialize in lipid-like molecules - Active learning fine-tuning within a closed-loop experimental system

1

Bo Wang @bowang87.bsky.social · Feb 18

🔬 What is LUMI-lab?
LUMI-lab integrates molecular foundation models with autonomous robotic experiments to efficiently explore new LNPs (lipid nanoparticles, mRNA delivery vehicles) with minimal wet-lab data.

1

Bo Wang @bowang87.bsky.social · Feb 18

How can generative AI and Robotics help advance drug discovery？

🚀 Excited to introduce LUMI-lab!
A foundation model-driven Self-Driving Lab (SDL) for autonomous ionizable lipid discovery in mRNA delivery 🤖🔍

1 1 2

Bo Wang @bowang87.bsky.social · Feb 18

🎉 Results speak for themselves:
- 63.1% accuracy on ChestAgentBench
- State-of-the-art performance on CheXbench
- Outperforms both general-purpose and specialized medical models

🙏 Huge shoutout to
Adibvafa, Jun, Alif, and Hongwei for their exceptional work on this project!

3

Bo Wang @bowang87.bsky.social · Feb 18

📊 Introducing ChestAgentBench:

We're also releasing ChestAgentBench, a comprehensive medical agent benchmark built from 675 expert-curated clinical cases, featuring 2,500 complex medical queries across 7 categories.

Check it out: huggingface.co/datasets/wan...

1 3

Bo Wang @bowang87.bsky.social · Feb 18

💡 Key Features:
- Unified Framework: Seamlessly integrates specialized medical tools with multimodal large language model reasoning.
- Dynamic Orchestration: Intelligent tool selection and coordination for complex queries.
- Clinical Focus: Designed for real-world medical workflows and deployment.

1 1

Bo Wang @bowang87.bsky.social · Feb 18

🛠️ Integrated Tools:

- Visual QA: CheXagent & LLaVA-Med
- Segmentation: MedSAM & ChestX-Det
- Report Generation: CheXpert Plus
- Classification: TorchXRayVision
- Grounding: Maira-2
- Synthetic Data: RoentGen

1 1

Bo Wang @bowang87.bsky.social · Feb 18

🎯 Why MedRAX?

While specialized AI models excel at specific chest X-ray tasks, they often operate in isolation. Medical professionals need a unified, reliable system that can handle complex queries while maintaining accuracy. MedRAX bridges this gap!

1 1

Bo Wang @bowang87.bsky.social · Feb 18

What is MedRAX?

MedRAX is the first versatile AI agent that seamlessly integrates state-of-the-art chest X-ray analysis tools and multimodal large language models into a unified framework, enabling dynamic reasoning for complex medical queries without additional training.

2 1

Bo Wang @bowang87.bsky.social · Feb 18

Agentic AI Meets Medicine!!!

🔬 Excited to announce MedRAX: a groundbreaking Medical Reasoning Agent for Chest X-ray interpretation, now on arXiv!

Paper:https://arxiv.org/abs/2502.02673

Code: github.com/bowang-lab/M...

1 1 7

Bo Wang @bowang87.bsky.social · Feb 17

Huge shoutout to the incredible PHD students Chloe Wang and Haotian Cui for leading this groundbreaking project! 🎉

Massive thanks to our amazing co-authors Andrew, Ronald, and Hani ( @genophoria.bsky.social )from
@arcinstitute.org
—this work wouldn't have been possible without you! 👏

1

Bo Wang @bowang87.bsky.social · Feb 17

📄 Read the preprint: biorxiv.org/content/10.1...
💻 Explore the code/weights: github.com/bowang-lab/s...

#SpatialTranscriptomics #SingleCell #AIResearch #MachineLearning #SpatialData

scGPT-spatial: Continual Pretraining of Single-Cell Foundation Model for Spatial Transcriptomics

Spatial transcriptomics has emerged as a pivotal technology for profiling gene expression of cells within their spatial context. The rapid growth of publicly available spatial data presents an opportu...

biorxiv.org

1 1 3

Bo Wang @bowang87.bsky.social · Feb 17

✨ Multi-Modal & Multi-Slide Integration – Seamless clustering & spatial domain identification across slides and modalities.
✨ Cell-Type Deconvolution & Gene Imputation – Unlocks cross-resolution & cross-modality harmonization with fine-tuned embeddings.

1 1

Bo Wang @bowang87.bsky.social · Feb 17

✨ Revolutionary MoE Decoders – A cutting-edge Mixture of Experts (MoE) architecture for protocol-aware gene expression decoding.
✨ Spatially-Aware Training Strategy – A neighborhood-based masked reconstruction approach to capture complex cell-type colocalization.

1 2